Gents,
We want to understand the mechanism of zfs a bit better.
Q: what is the design/algorithm of zfs in terms of reclaiming unused
blocks?
Q: what criteria is there for zfs to start reclaiming blocks
Issue at hand is an LDOM or zone running in a virtual
(thin-provisioned) disk on a NFS server and a zpool inside that vdisk.
This vdisk tends to grow in size even if the user writes and deletes a
file again. Question is, whether this reclaiming of unused blocks can
kick in earlier, so that the filesystem doesn''t grow much more than
what is actually allocated?
Thanks,
heinz
--
Heinz Zerbes
Security Consultant and Auditor
Sun Microsystems Australia
33 Berry St., North Sydney, NSW 2060 AU
Phone x59468/+61 2 9466 9468
Mobile +61 410 727 961
Fax +61 2 9466 9411
Email Heinz.Zerbes@Sun.COM
_______________________________________________
zfs-discuss mailing list
zfs-discuss@opensolaris.org
http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
Gents, We want to understand the mechanism of zfs a bit better. Q: what is the design/algorithm of zfs in terms of reclaiming unused blocks? Q: what criteria is there for zfs to start reclaiming blocks Issue at hand is an LDOM or zone running in a virtual (thin-provisioned) disk on a NFS server and a zpool inside that vdisk. This vdisk tends to grow in size even if the user writes and deletes a file again. Question is, whether this reclaiming of unused blocks can kick in earlier, so that the filesystem doesn''t grow much more than what is actually allocated? Thanks, heinz
On Feb 15, 2010, at 8:43 PM, heinz zerbes wrote:> > Gents, > > We want to understand the mechanism of zfs a bit better. > > Q: what is the design/algorithm of zfs in terms of reclaiming unused blocks? > Q: what criteria is there for zfs to start reclaiming blocksThe answer to these questions is too big for an email. Think of ZFS as a very dynamic system with many different factors influencing block allocation.> Issue at hand is an LDOM or zone running in a virtual (thin-provisioned) disk on a NFS server and a zpool inside that vdisk. > This vdisk tends to grow in size even if the user writes and deletes a file again. Question is, whether this reclaiming of unused blocks can kick in earlier, so that the filesystem doesn''t grow much more than what is actually allocated?ZFS is a COW file system, which partly explains what you are seeing. Snapshots, deduplication, and the ZIL complicate the picture. -- richard ZFS storage and performance consulting at http://www.RichardElling.com ZFS training on deduplication, NexentaStor, and NAS performance http://nexenta-atlanta.eventbrite.com (March 15-17, 2010)
Richard, thanks for the heads-up. I found some material here that sheds a bit more light on it: http://en.wikipedia.org/wiki/ZFS http://all-unix.blogspot.com/2007/04/transaction-file-system-and-cow.html Regards, heinz Richard Elling wrote:> On Feb 15, 2010, at 8:43 PM, heinz zerbes wrote: > >> Gents, >> >> We want to understand the mechanism of zfs a bit better. >> >> Q: what is the design/algorithm of zfs in terms of reclaiming unused blocks? >> Q: what criteria is there for zfs to start reclaiming blocks >> > > The answer to these questions is too big for an email. Think of > ZFS as a very dynamic system with many different factors influencing > block allocation. > > >> Issue at hand is an LDOM or zone running in a virtual (thin-provisioned) disk on a NFS server and a zpool inside that vdisk. >> This vdisk tends to grow in size even if the user writes and deletes a file again. Question is, whether this reclaiming of unused blocks can kick in earlier, so that the filesystem doesn''t grow much more than what is actually allocated? >> > > ZFS is a COW file system, which partly explains what you are seeing. > Snapshots, deduplication, and the ZIL complicate the picture. > -- richard > > > ZFS storage and performance consulting at http://www.RichardElling.com > ZFS training on deduplication, NexentaStor, and NAS performance > http://nexenta-atlanta.eventbrite.com (March 15-17, 2010) > > > >